Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15599
    Prev
    Next
    INDEX
    Explanations

    verbs and their usage in various contexts, particularly in reference to existence and characteristics of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     samman
    -0.59
     GreatSchools
    -0.57
     atteinte
    -0.55
     kennis
    -0.55
    garmin
    -0.54
     isolada
    -0.54
     traccia
    -0.53
     seules
    -0.52
    раздо
    -0.52
     marinho
    -0.51
    POSITIVE LOGITS
     BoxDecoration
    0.80
     really
    0.73
    __(/*!
    0.69
     good
    0.69
     pretty
    0.68
    rawDesc
    0.67
    ezers
    0.67
     funny
    0.66
     gonna
    0.65
    thenReturn
    0.65
    Activations Density 0.173%

    No Known Activations